add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,73 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- glue
+metrics:
+- spearmanr
+model_index:
+- name: stsb
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE STSB
+      type: glue
+      args: stsb
+    metric:
+      name: Spearmanr
+      type: spearmanr
+      value: 0.9050744778895732
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# stsb
+
+This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the GLUE STSB dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3978
+- Pearson: 0.9090
+- Spearmanr: 0.9051
+- Combined Score: 0.9071
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 64
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.9.0
+- Pytorch 1.9.0+cu102
+- Datasets 1.10.2
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 4.0,
+    "eval_combined_score": 0.9070512696741792,
+    "eval_loss": 0.3978178799152374,
+    "eval_pearson": 0.9090280614587851,
+    "eval_runtime": 13.6802,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 109.648,
+    "eval_spearmanr": 0.9050744778895732,
+    "eval_steps_per_second": 13.743,
+    "train_loss": 0.43474773830837676,
+    "train_runtime": 506.7423,
+    "train_samples": 5749,
+    "train_samples_per_second": 45.38,
+    "train_steps_per_second": 0.71
+}

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "albert-base-v2",
+  "architectures": [
+    "AlbertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "finetuning_task": "stsb",
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "regression",
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.0",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 4.0,
+    "eval_combined_score": 0.9070512696741792,
+    "eval_loss": 0.3978178799152374,
+    "eval_pearson": 0.9090280614587851,
+    "eval_runtime": 13.6802,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 109.648,
+    "eval_spearmanr": 0.9050744778895732,
+    "eval_steps_per_second": 13.743
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6fc22d84559cadd2b5bce10cc8caac94c27da6d99c529d76bf426f3179425fd
+size 46752465

runs/Jul26_10-48-21_87e5b6406975/1627296525.161824/events.out.tfevents.1627296525.87e5b6406975.485.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:778b654c978867b2cb0d7a9c4a094ebe63ccaa4843767412b60b2d1d53b98784
+size 4167

runs/Jul26_10-48-21_87e5b6406975/events.out.tfevents.1627296525.87e5b6406975.485.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cde7b06c86b4876bfd8bdc13d98596a6c5fbb3e0ec86ebbc8c57a4e997825d38
+size 3548

runs/Jul26_10-48-21_87e5b6406975/events.out.tfevents.1627297045.87e5b6406975.485.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b52aabf9d844fae40928fec3984949d7fe04cc3ab4b022e11c0a6efedb66424
+size 473

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "remove_space": true, "keep_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "albert-base-v2", "tokenizer_class": "AlbertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.43474773830837676,
+    "train_runtime": 506.7423,
+    "train_samples": 5749,
+    "train_samples_per_second": 45.38,
+    "train_steps_per_second": 0.71
+}

trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 360,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 4.0,
+      "step": 360,
+      "total_flos": 137376605764608.0,
+      "train_loss": 0.43474773830837676,
+      "train_runtime": 506.7423,
+      "train_samples_per_second": 45.38,
+      "train_steps_per_second": 0.71
+    }
+  ],
+  "max_steps": 360,
+  "num_train_epochs": 4,
+  "total_flos": 137376605764608.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c592deb26553180813296cece5490d0e30ccd681013f57a4a94259490592f22
+size 2607